Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    legal/formal language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .until
    -0.07
     moisture
    -0.06
    ศา
    -0.06
    电子商务
    -0.06
    自卑
    -0.06
     фактор
    -0.06
    ORA
    -0.06
    (CONFIG
    -0.06
    NamedQuery
    -0.06
     dragging
    -0.06
    POSITIVE LOGITS
    滨州
    0.07
     apologized
    0.07
    being
    0.07
    LEAR
    0.07
    젔
    0.06
    <Base
    0.06
    ipzig
    0.06
     في
    0.06
    .GetAll
    0.06
    loses
    0.06
    Act Density 0.148%

    No Known Activations